← 최신 프로덕트

TurboGPT

train 22KiB transformer in 13s. Train a tiny GPT in under a minute (CUDA only). Inspired by minGPT for home experiments.

오픈소스

56 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. less than 650 LOC trainable GPT only using NumPy

    github.com

    Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).

    Hacker News90점

  2. FemtoGPT

    github.com

    Pure Rust implementation of a GPT language model

    Hacker News19점

  3. Minimal LLM Post-Training Experiments on an 8GB GPU (SFT

    github.com

    DPO, GRPO)

    Hacker News21점

  4. Lemon Slice Live

    news.ycombinator.com

    Have a video call with a transformer model

    Hacker News195점

  5. TinyGPT

    github.com

    A Simple, Educational Deep Learning Library

    Hacker News13점